)il#SrSSKrSSKrSSKJr SSKJrJrJrJ r J r J r SSK J r JrJrJrJr SSKJr SSKJrJr SS KJrJr SS KJrJr SS KJr SS KJ r J!r!J"r" S#S \S\"S\#S\#S\ \S\$S\ \\$S\#S\%S\$S\#S\ \#S\&S\&S\&S\SS4"Sjjr'S$S\!S\#S\ \\$S\$S \&S\#S\ \S\#4S!jjr(S%S\!S\#S\ \\$S\$S \&S\ \S\ \4S"jjr)g)&zIFunctions that can be used for the most common use-cases for pdfminer.sixN)StringIO)AnyBinaryIO ContainerIteratorOptionalcast) XMLConverter HTMLConverter TextConverterPDFPageAggregator HOCRConverter) ImageWriter)LAParamsLTPage) PDFDevice TagExtractor)PDFResourceManagerPDFPageInterpreter)PDFPage) open_filename FileOrNameAnyIOinfoutfp output_typecodeclaparamsmaxpages page_numberspasswordscalerotation layoutmode output_dir strip_controldebugdisable_cachingkwargsreturnc U (a2[R"5R[R5 SnU (a [ U 5n[ U(+S9nSnUS:wa.U[ R:Xa[ RRnUS:Xa [UXUUS9nOmUS:Xa[UUUUUU S9nOXUS:Xa[UUUUU UUS9nOBUS :Xa [UXXLS 9nO0US :Xa[U[[U5US 9nOS U3n[!U5eUce[#UU5n[$R&"UUUUU(+S9H+nUR(U -S-UlUR+U5 M- UR-5 g)aParses text from inf-file and writes to outfp file-like object. Takes loads of optional arguments but the defaults are somewhat sane. Beware laparams: Including an empty LAParams is not the same as passing None! :param inf: a file-like object to read PDF structure from, such as a file handler (using the builtin `open()` function) or a `BytesIO`. :param outfp: a file-like object to write the text to. :param output_type: May be 'text', 'xml', 'html', 'hocr', 'tag'. Only 'text' works properly. :param codec: Text decoding codec :param laparams: An LAParams object from pdfminer.layout. Default is None but may not layout correctly. :param maxpages: How many pages to stop parsing after :param page_numbers: zero-indexed page numbers to operate on. :param password: For encrypted PDFs, the password to decrypt. :param scale: Scale factor :param rotation: Rotation factor :param layoutmode: Default is 'normal', see pdfminer.converter.HTMLConverter :param output_dir: If given, creates an ImageWriter for extracted images. :param strip_control: Does what it says on the tin :param debug: Output more logging data :param disable_caching: Does what it says on the tin :param other: :return: nothing, acting as it does on two streams. Use StringIO to get strings. Ncachingtext)rr imagewriterxml)rrr0 stripcontrolhtml)rr#r%rr0hocr)rrr2tag)rz1Output type can be text, html, xml or tag but is r r"r.ih)logging getLoggersetLevelDEBUGrrsysstdoutbufferr r r rrr r ValueErrorrr get_pagesrotate process_pageclose)rrrrrr r!r"r#r$r%r&r'r(r)r*r0rsrcmgrdevicemsg interpreterpages S/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/pdfminer/high_level.pyextract_text_to_fprIs^ $$W]]3K!*-  _)<=G"&Ff#**!4 !!f U(      #&      !#    U(   gtHe'"#3G()9B %% xG D  $ $T *&&(FL  ' & &sB&A0B B& B#B&) r/utf-8NrNg?rnormalNFFF)rXNrTrWN)rXNrTN)*__doc__r7r;iortypingrrrrrr converterr r r rrimagerrUrr pdfdevicerr pdfinterprrpdfpagerutilsrrrstrintfloatboolrIrQrVrJrHrhsO EE$.=33 #'-1 $!o o oo  o x o  o9S>*oo ooo oo oo !o" #oh-1#'((((((9S>*(( ((  ((  ((x (( ((Z-1#' !!!9S>*! !  ! x !f!rJ